Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/queelius/claude-anvil/scribenpx skills add queelius/claude-anvil --skill scribegit clone --depth 1 https://github.com/queelius/claude-anvilWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/queelius/claude-anvil/scribe)<a href="https://agentmods.dev/skills/queelius/claude-anvil/scribe"><img src="https://agentmods.dev/badge/skills/queelius/claude-anvil/scribe.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00113 | $0.01905 |
| Opus 5 | $0.00056 | $0.00953 |
| Sonnet 5 | $0.00023 | $0.00381 |
| Haiku 4.5 | $0.00011 | $0.00191 |
Grade A, and why
scribe scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scribe: latent theme discovery
The smallest useful agent: find threads in your own corpus that you did not realize you had already written.
What this does (and doesn't)
Does: scans every post in the metafunctor content/post/ directory, returns 3 candidate themes that connect at least 4 posts each, each with a one-sentence through-line and a list of source posts.
Does NOT: write a draft. The output is a proposal you accept or reject. If you accept one, you tell me to expand it; we iterate from there. The smallest scribe stops at "here are the candidates."
This is intentional. Voice fidelity is hard. Validating that the corpus has interesting structure is easy. Do the easy thing first; if the candidates feel real, we build the drafting layer next.
Workflow
1. Read the corpus
Get title, date, description, and tags for every post. Three paths, in preference order:
mf posts list --json(primary): one Bash call returns the whole corpus as a JSON array withslug,title,date,description,tags(plus categories/series/featured/draft). Works from any directory (mf resolves the site root itself), and the scribe filters map natively:/scribe 5y(time window):mf posts list --json --since <ISO date>(or months, e.g.60m; the CLI acceptsYYYY-MM-DDor30d/4w/3mforms, not years)/scribe --tag philosophy:mf posts list --json -t philosophy- Requires an mf build that includes
descriptionin the JSON (added 2026-06-09); ifdescriptionis missing from the output, fall through.
crier_search(if the crier plugin is installed):crier_search(limit=300).- Glob fallback (fully self-contained): resolve the metafunctor site root the way the
mfskill does (theMF_SITE_ROOTenv var, or the configured site root), thenGlobcontent/post/**/index.mdand read the YAML front matter.
You only need title, date, description, and tags; do not read post bodies for the smallest scribe. Default is the full corpus.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago First seen · 130 lines · 113 tokens per session scan A ae72bdd6ebbe
scribe is a skill published in the GitHub repository queelius/claude-anvil (2 stars, last pushed 1mo ago), licensed MIT. It adds 113 tokens to every session and 1,905 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
alive:demo
Generate a believable, lived-in ALIVE world from a free-text persona description (custom path) or a deterministic sandbox preset. Routes the create/list/activate/deactivate/delete/status surface and orchestrates the 5-stage subagent generation pipeline.
alive:system-upgrade
Upgrade ALIVE to the current version. Handles v1/v2/v3.x source states, multi-surface aware (alive-mcp / Hermes / Codex), retroactive version detection, partial-failure resume, dry-run previews, and rollback inspection.
alive:session-history
Revive sessions (quick or heavy), browse, and search — 'what happened recently?', 'find the session where we discussed X', 'revive yesterday's session'. For single-session recall and multi-session browsing. If the human needs to merge multiple sessions into one working context or detect conflicts between parallel…
alive:world
The human doesn't know what to work on, or wants to see everything at once. They need the big picture — what's active, what's stale, what needs attention. Renders a live world view grouped by ALIVE domain, then routes to open, tidy, find, history, or map.
cco-task
Organize work by task, track tokens/cost per task, and keep a small patchable execution state that is re-injected after /compact (SKILL.state-style) — start a task, patch its state, list tasks, or mark the active one done. Pairs with /cco-pack to load minimal context per task.
cco-tools
Show what tools actually cost in tokens — learned per-tool averages from observed results, replacing the hardcoded MCP/Agent guesses.